Saved in:
Bibliographic Details
Main Authors: Roschkowski, Marco, Cherifi, Karim, Gernandt, Hannes
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.20447
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914420813201408
author Roschkowski, Marco
Cherifi, Karim
Gernandt, Hannes
author_facet Roschkowski, Marco
Cherifi, Karim
Gernandt, Hannes
contents The use of machine learning models in system identification has increased due to their ability to approximate complex nonlinear dynamics with high accuracy. However, often it is not clear how the performance of trained models scales with given resources such as data, compute, and model size. To allow for a better understanding of the scalability of the performance of machine learning models, we verify neural scaling laws (NSLs) in the context of system identification from input-state-output data using different evaluation metrics for accuracy and different system architectures, including input-affine and physics-informed port-Hamiltonian representations. Our verified NSLs can help to forecast performance improvements and guide model design or data acquisition.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20447
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Scaling Laws for Learning-based Identification of Nonlinear Systems
Roschkowski, Marco
Cherifi, Karim
Gernandt, Hannes
Optimization and Control
The use of machine learning models in system identification has increased due to their ability to approximate complex nonlinear dynamics with high accuracy. However, often it is not clear how the performance of trained models scales with given resources such as data, compute, and model size. To allow for a better understanding of the scalability of the performance of machine learning models, we verify neural scaling laws (NSLs) in the context of system identification from input-state-output data using different evaluation metrics for accuracy and different system architectures, including input-affine and physics-informed port-Hamiltonian representations. Our verified NSLs can help to forecast performance improvements and guide model design or data acquisition.
title Neural Scaling Laws for Learning-based Identification of Nonlinear Systems
topic Optimization and Control
url https://arxiv.org/abs/2512.20447